claude-mem-lite: Instructions file for Claude Code

CLAUDE.md

claude-mem-lite CLAUDE.md is an instructions file for Claude Code from sdsrss/claude-mem-lite. It costs 26,081 tokens per session, scanned A, original, MIT.

Project instructions for Claude Code that explain the claude-mem-lite memory system, its structure, health checks, and where new code belongs.

In plain words
What is it for?
Maintaining claude-mem-lite, running its tests, lint checks, benchmarks, and memory-quality comparisons.
Why use it?
It gives the coding agent a consistent guide to the project, reducing confusion about architecture, commands, tests, and code placement.

Instructions file for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is sdsrss/claude-mem-lite's own configuration. It tells Claude Code how to work on claude-mem-lite itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything claude-mem-lite configures →

Reuse

Borrowing it

Nothing to install: this file belongs to sdsrss/claude-mem-lite. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/sdsrss/claude-mem-lite/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/sdsrss/claude-mem-lite

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for claude-mem-lite CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/sdsrss/claude-mem-lite/claude-md.svg)](https://agentmods.dev/instructions/sdsrss/claude-mem-lite/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/sdsrss/claude-mem-lite/claude-md"><img src="https://agentmods.dev/badge/instructions/sdsrss/claude-mem-lite/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 26,081 This file is loaded in full into every session.
When invoked 26,081 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.26081 $0.26081
Opus 5 $0.13040 $0.13040
Sonnet 5 $0.05216 $0.05216
Haiku 4.5 $0.02608 $0.02608

Measured today against content hash ba479eec409b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

claude-mem-lite CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 816 lines

How it starts

The opening of the file, as written. The whole thing — 816 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Lightweight persistent memory system for Claude Code. MCP server + hooks plugin.

  • Version: 5.5.1 — this exact string is a release guard. tests/install-e2e.test.mjs asserts CLAUDE.md contains **Version**: <v> matching package.json, plugin.json and marketplace.json. Do not reformat this line.
  • Runtime: Node >=22 (20 dropped in v4.0.0; EOL 2026-04 and better-sqlite3 13 requires >=22), ESM ("type": "module") · npm · better-sqlite3 + FTS5

Commands

Task Command
Setup npm install (needs a Node >=22 toolchain; native better-sqlite3 binding must build)
All tests npx vitest run — or npm test
One file npx vitest run tests/foo.test.mjs
One case npx vitest run -t 'case name'
Smoke only npm run test:smoke
Coverage npm run test:coverage (gate: statements 81 / branches 75 / functions 87 / lines 83)
Lint npx eslint . — or npm run lint
Format npm run format (prettier — run it twice, tests/hook-update.test.mjs needs a second pass to reach a fixed point) · npm run format:checkgated in ci.yml and scripts/pre-commit.sh since the 2026-09-05 reformat
Dead code npm run dead-code (knip — read the measurement contract below first)
Shell shellcheck scripts/post-tool-use.sh scripts/pre-agent-inject.sh scripts/pre-commit.sh scripts/setup.sh
Micro-bench npm run benchmark (node benchmark/benchmark.mjs) · CI gate: npm run benchmark:gate (benchmark/ci-gate.mjs)
Multiplier wiring npm run benchmark:multipliers · npm run benchmark:multipliers:gate (--self-check, exits 1). Run this after touching any constant in scoring-sql.mjs or MULT_EXPRbenchmark:gate is structurally blind to those, see the invariant below
Recapture the gate baseline node benchmark/benchmark.mjs --production-hybrid > benchmark/baseline.jsonbenchmark/baseline.json EXPIRES 30 days after its own timestamp, and both ci.yml (on push) and publish.yml pass --strict, which turns that into a hard failure. Sampled 2026-09-07T08:00:55Z (f89520c, recaptured at 203a426) → red from 2026-10-07 08:00 UTC. The stamp lives in THREE places, not twobenchmark/baseline.json's own timestamp, ci.yml:132, and this line — and they must be changed together. 203a426 moved the first two and left this one naming the previous sample, in a commit whose own message cites R10 P3-23's "a hand-copied stamp goes stale silently"; the third surface was simply never enumerated. tests/baseline-stamp-sync.test.mjs now derives the expiry from baseline.json + the gate's own BASELINE_STALE_AGE_DAYS and fails if either prose surface disagrees, so this is enforced rather than remembered. In the release path the failure lands after the tag is pushed (v3.69.0/v3.69.1 stalled on exactly this), so recapture BEFORE tagging, in its own commit, naming the sampled tree.
Audit metrics npm run audit:metrics · npm run audit:baseline

Read the full file on GitHub · 816 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. today Changed · +459 lines · +18,140 tokens per session ba479eec409b
  2. yesterday Changed · +164 lines · -18,330 tokens per session 570f3ead4757
  3. 2d ago Changed · -1 lines · +1,081 tokens per session 08c7841dd3a3
  4. 4d ago Changed · +29 lines · +15,576 tokens per session c6f5ed91e2ab
  5. 8d ago First seen · 165 lines · 9,614 tokens per session scan A b412932956b3

Subscribe to this mod's changes

claude-mem-lite CLAUDE.md is an instructions file published in the GitHub repository sdsrss/claude-mem-lite (58 stars, last pushed today), licensed MIT. It adds 26,081 tokens to every session, about $0.1304 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens